Gaussian process modelling as an indicator of neonatal seizure

Authors:
Stephen Faul;Gregor Gregorčič;Geraldine Boylan;William Marnane;Gordon Lightbody;Sean Connolly
Affiliations:
Dept. of Electrical and Electronic Engineering, University College, Cork, Ireland;Dept. of Electrical and Electronic Engineering, University College, Cork, Ireland;Dept. of Paediatrics and Child Health, University Hospital, Cork, Ireland;Dept. of Electrical and Electronic Engineering, University College, Cork, Ireland;Dept. of Electrical and Electronic Engineering, University College, Cork, Ireland;Dept. of Clinical Neurophysiology, St. Vincents Hospital, Dublin, Ireland
Venue:
SPPRA'06 Proceedings of the 24th IASTED international conference on Signal processing, pattern recognition, and applications
Year:
2006

Citing 3
Cited 1

An adaptive structure neural networks with application to EEG automatic seizure detection

Neural Networks
Feature Selection sing a Mutual Information Based Measure

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 4 - Volume 4
Newborn EEG seizure pattern characterisation using time-frequency analysis

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 200. on IEEE International Conference - Volume 02

Nonlinear system identification: From multiple-model networks to Gaussian processes

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gaussian process models have some attractive advantages over parametric models and neural networks. They have a small number of tunable parameters, give a measure of the uncertainty of the model prediction, and obtain a relatively good model when only a small set of training data is available. In this study the theory of Gaussian process models has been applied to the neonatal seizure detection problem. Two measures are calculated from 1 second windows of EEG recordings; the variance (certainty) of a one step ahead prediction, and the ratio of the first model hyperparameter to the last. In ANOVA tests both measures show statistical difference in their values for nonseizure and seizure EEG. A comparison with a similar Autoregressive (AR) modelling approach shows that Gaussian Process model methods show great promise in real-time neonatal seizure detection.